balance_rows

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint/idempotent/non-destructive, so the safety profile is covered. The description adds real value beyond that by describing the payload shape (all account codes, names, and 10 debit/credit numeric columns), which is the only return-value documentation since no output schema exists. It omits any mention of row count limits or pagination.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core action and followed by the return contents, with zero filler. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, closed-world lookup with fully documented parameters, the description is nearly complete: it covers action, output contents, and a verification use case. The remaining gap is its relationship to the other balance_* tools and any row-volume caveats.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both id and companyId fully documented in the schema including the env-var override behavior. The description adds nothing about either parameter, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: retrieves the parsed account rows of a trial balance, and even enumerates the returned fields. It does not, however, differentiate itself from nearby siblings like balance_list or balance_analysis, leaving the agent to infer that this is the raw-row view rather than the aggregate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Useful for verifying PDF parsing results" implies a verification use case, but there is no explicit when-to-use vs. balance_analysis and no statement that the required id must first be obtained via balance_list. Usage is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.